© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48432
    Prev
    Next
    INDEX
    Explanations

    Okay, let's verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    잌
    0.36
     plat
    0.35
     кантора
    0.34
     lock
    0.34
    withstanding
    0.34
    川
    0.34
     engineer
    0.34
     બંધ
    0.34
     plow
    0.33
    િવ
    0.33
    POSITIVE LOGITS
    軹
    0.42
    ála
    0.37
    了解
    0.36
    ਵੇਂ
    0.35
    洧
    0.35
    ">>
    0.35
     Admir
    0.35
    相對
    0.35
    ாய்ச்சி
    0.35
     понимать
    0.34
    Activations Density 0.031%

    No Known Activations